fix(patch): cherry-pick 665228e to release/v0.45.0-pr-27570 to patch version v0.45.0 and create version 0.45.1#27667
Conversation
|
📊 PR Size: size/XL
|
gemini-cli-robot
temporarily deployed
to
eval-gate
GitHub Actions
Inactive
|
Size Change: +5.71 kB (+0.02%) Total Size: 33.9 MB
ℹ️ View Unchanged
|
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request cherry-picks essential updates to patch version v0.45.0, primarily introducing support for the gemini-3.5-flash model. It includes comprehensive updates to model configurations, policy resolution logic, and schema definitions. Additionally, it refines the LLM judge's response parsing and fixes a resource cleanup issue in shell tool invocations for background processes. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize the Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces support for the gemini-3.5-flash model, updating configuration files, schemas, and model resolution logic to dynamically route flash requests when GA access is enabled. It also updates the shell tool to prevent cleaning up temporary files for background processes, and refactors the response parsing in evals/llm-judge.ts. Feedback on the changes highlights a potential false positive issue in the LLM judge's string matching logic, recommending a more robust standalone word check. Additionally, the reviewer points out that the new configuration tests mutate global state, suggesting the addition of an afterEach block to reset the flash models and prevent test flakiness.
|
✅ 69 tests passed successfully on gemini-3-flash-preview. 🧠 Model Steering GuidanceThis PR modifies files that affect the model's behavior (prompts, tools, or instructions).
This is an automated guidance message triggered by steering logic signatures. |
… 3.5 flash when the flag is enabled. (#27645)
gemini-cli
Bot
added
the
status/need-issue
galdawave
deleted the
hotfix/v0.45.0/0.45.1/stable/cherry-pick-665228e/pr-27570
branch
4 participants
This PR automatically cherry-picks commit 665228e and e4315b3 to patch version v0.45.0 in the stable release to create version 0.45.1.
This is needed to give 3.5 flash access to users of the stable channel, as it is already in preview.